Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14025
    Prev
    Next
    INDEX
    Explanations

    financial activities and economic performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.65
    setVerticalGroup
    -0.60
    ⓧ
    -0.58
     transfieras
    -0.57
     Instantly
    -0.57
    Trag
    -0.56
     désolés
    -0.56
     Trag
    -0.54
     honte
    -0.54
    บัติ
    -0.53
    POSITIVE LOGITS
     strong
    1.21
     demand
    1.09
     robust
    0.99
     buoyant
    0.98
    Strong
    0.97
     optimism
    0.96
    Demand
    0.96
     stronger
    0.94
     Strong
    0.92
    strong
    0.92
    Activations Density 0.144%

    No Known Activations